Grounded Lexicon Acquisition - Case Studies in Spatial Language

TL;DR

This paper presents experiments on how humanoid robots can learn various spatial language systems from tutors without direct meaning transfer, demonstrating simultaneous acquisition of multiple systems of increasing complexity.

Contribution

It introduces a novel learning approach enabling robots to acquire multiple spatial language systems simultaneously without direct access to world models.

Findings

Robots successfully learned projective, absolute, and proximal spatial systems.

Multiple spatial language systems can be acquired concurrently.

The learning mechanism does not depend on direct meaning transfer or world model access.

Abstract

This paper discusses grounded acquisition experiments of increasing complexity. Humanoid robots acquire English spatial lexicons from robot tutors. We identify how various spatial language systems, such as projective, absolute and proximal can be learned. The proposed learning mechanisms do not rely on direct meaning transfer or direct access to world models of interlocutors. Finally, we show how multiple systems can be acquired at the same time.